© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    release dates and related information for video games, movies, albums, and other media

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.77
    kos
    -0.74
     subsistence
    -0.64
    mong
    -0.63
    involved
    -0.61
     Howe
    -0.60
     Column
    -0.55
    ratom
    -0.54
    usra
    -0.53
    otin
    -0.53
    POSITIVE LOGITS
     theat
    1.05
     concurrently
    1.01
     worldwide
    0.96
     alongside
    0.95
     digitally
    0.90
     sometime
    0.89
     simultaneously
    0.87
     exclusively
    0.87
    ruary
    0.86
     commercially
    0.85
    Activations Density 0.096%

    No Known Activations